2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2022 · 738 citations · 40 references
ComputingRobotics EngineeringComputer VisionRobot PerceptionRobot Vision3D ReconstructionIndoor LocalizationMappingScene ReconstructionScene UnderstandingSimultaneous LocalizationBenchmark DatasetsHierarchical Space RepresentationNeural Encoding ModelsScene Representation
Neural implicit representations have recently shown encouraging results in various domains, including promising progress in simultaneous localization and mapping (SLAM). Nevertheless, existing methods produce over- smoothed scene reconstructions and have difficulty scaling up to large scenes. These limitations are mainly due to their simple fully-connected network architecture that does not incorporate local information in the observations. In this paper, we present NICE-SLAM, a dense SLAM system that incorporates multi-level local information by introducing a hierarchical scene representation. Optimizing this representation with pre-trained geometric priors enables detailed reconstruction on large indoor scenes. Compared to recent neural implicit SLAM systems, our approach is more scalable, efficient, and robust. Experiments on five challenging datasets demonstrate competitive results of NICE-SLAM in both mapping and tracking quality. Project page: https://pengsongyou.github.io/nice-slam.
40
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
Angela Dai, Manolis Savva, Maciej Halber et al. · 2017 · 4K citations
KinectFusion: Real-time dense surface mapping and tracking
Richard A. Newcombe, Andrew Fitzgibbon, Shahram Izadi et al. · 2011 · 3.9K citations
A benchmark for the evaluation of RGB-D SLAM systems
Jrgen Sturm, Nikolas Engelhard, Felix Endres et al. · 2012 · 3.9K citations
A volumetric method for building complex models from range images
Brian Curless, Marc Levoy · 1996 · 3.1K citations